| { | |
| "architectures": [ | |
| "LuminousForEmbedding" | |
| ], | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "attn_adapter_config": { | |
| "hidden_act": "gelu", | |
| "hidden_size": 4608, | |
| "intermediate_size": 1152, | |
| "mlp_bias": false | |
| }, | |
| "bias_name": null, | |
| "bos_token_id": 1, | |
| "causal_attention": true, | |
| "embedding_head_out": null, | |
| "eos_token_id": 2, | |
| "hidden_act": "gelu", | |
| "hidden_size": 4608, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18432, | |
| "layer_norm_epsilon": 1e-05, | |
| "lora_config": null, | |
| "max_position_embeddings": 8192, | |
| "mlp_adapter_config": { | |
| "hidden_act": "gelu", | |
| "hidden_size": 4608, | |
| "intermediate_size": 1152, | |
| "mlp_bias": false | |
| }, | |
| "mlp_bias": true, | |
| "mode": "generation", | |
| "num_attention_heads": 36, | |
| "num_hidden_layers": 27, | |
| "num_key_value_heads": 4, | |
| "pooling_method": "weighted_mean", | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.47.0", | |
| "use_cache": false, | |
| "vocab_size": 128000 | |
| } | |